Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    lack of confirmation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ');
    -0.07
    setItem
    -0.07
     scholar
    -0.07
     hätte
    -0.07
    (ph
    -0.07
     Avery
    -0.06
    _PASSWORD
    -0.06
     BEN
    -0.06
    ]?
    -0.06
     adopted
    -0.06
    POSITIVE LOGITS
     pocházet
    0.07
    illon
    0.07
    BoundingBox
    0.06
     대전
    0.06
     dl
    0.06
     vedení
    0.06
    غاز
    0.06
    details
    0.06
     Mik
    0.06
     broth
    0.06
    Act Density 0.023%

    No Known Activations